检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Xiran Zhang, Jian Qi, Lei Shi, Yinghuan The State Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University China The School of Computer Science and Engineering Southeast University China

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario where the source and target domains have different classes. To overcome this deficiency, open set domain generalization (OSDG) then emerges as a more practical setting to recognize unseen classes in unseen domains. An intuitive approach is to use multiple one-vs-all classifiers to define decision boundaries for each class and reject the outliers as unknown. However, the significant class imbalance between positive and negative samples often causes the boundaries biased towards positive ones, resulting in misclassification for known samples in the unseen target domain. In this paper, we propose a novel meta-learning-based framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers gradient matching towards inter-domain and inter-class splits simultaneously to find a generalizable boundary balanced for all tasks. Experimental results demonstrate that MEDIC not only outperforms previous methods in open set scenarios, but also maintains competitive close set generalization ability at the same time. Our code is available at https://***/zzwdx/MEDIC. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Low Voltage Switchable Bistable Twist Nematic Display

Low Voltage Switchable Bistable Twist Nematic Display

引用

The 2023 International Conference on Display technology, (ICDT 2023)

作者： Liu, Pengcheng Tseng, Man Chun Yeung, Fion Sze Yan Kwok, Hoi Sing State Key Laboratory of Advanced Displays and Optoelectronics Technologies Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong

The most common electronic paper technology is E-ink, which enables many novel applications such as e-readers, watches and electronic shelf labels. However, due to the TFT backplane driving and complex production processes, the cost of this technology is high, which limits its popularity. Recently, a low-cost π-bistable twist nematic (π- BTN) liquid crystal display with a high pretilt angle is proposed. It has the same structure and production method as an ordinary liquid crystal display. Passive driving enables the manufacture of high-resolution bistable displays without the use of thin-film transistors. Compared with the current bistable twist nematic display technology, the high pretilt angles structure helps to achieve a low-voltage and fast-respond bistable display. This wide viewing angle, high contrast and TFT-free display is a promising candidate for flexible displays. © 2023, John Wiley and Sons Inc. All rights reserved.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

DomainAdaptor: A novel Approach to Test-time Adaptation

DomainAdaptor: A Novel Approach to Test-time Adaptation

引用

International Conference on computer Vision (ICCV)

作者： Jian Zhang Lei Qi Yinghuan Shi Yang Gao State Key Laboratory for Novel Software Technology Nanjing University National Institute of Healthcare Data Science Nanjing University School of Computer Science and Engineering Southeast University

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test. In this paper, we investigate a more challenging task that aims to adapt a trained CNN model to unseen domains during the test. To maximumly mine the information in the test data, we propose a unified method called DomainAdaptor for the test-time adaptation, which consists of an AdaMixBN module and a Generalized Entropy Minimization (GEM) loss. Specifically, AdaMixBN addresses the domain shift by adaptively fusing training and test statistics in the normalization layer via a dynamic mixture co-efficient and a statistic transformation operation. To further enhance the adaptation ability of AdaMixBN, we design a GEM loss that extends the Entropy Minimization loss to better exploit the information in the test data. Extensive experiments show that DomainAdaptor consistently outperforms the state-of-the-art methods on four benchmarks. Furthermore, our method brings more remarkable improvement against existing methods on the few-data unseen domain. The code is available at https://***/koncle/DomainAdaptor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Sparse Interaction Modeling is an Anomaly Detection Problem

Multi-Agent Sparse Interaction Modeling is an Anomaly Detect...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chao Li Shaokang Dong Shangdong Yang Hongye Cao Wenbin Li Yang Gao State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science Nanjing University of Posts and Telecommunications Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University

Most real-world multi-agent tasks exhibit the characteristic of sparse interaction, wherein agents interact with each other in a limited number of crucial states while largely acting independently. Effectively modeling the sparse interaction and leveraging the learned interaction structure to instruct agents’ learning processes can enhance the efficiency of multi-agent reinforcement learning algorithms. However, it remains unclear how to identify these specific interactive states solely through trials and errors within current multi-agent tasks. To address this challenge, this paper introduces a novel algorithm called Sparse Interaction as Anomaly (SIA), which innovatively casts the sparse interaction modeling into an anomaly detection problem. The underlying intuition is that interactive states appear rarely in agents’ trajectories and exhibit distinct dynamics compared to other commonplace states. Building upon this insight, SIA first employs variational inference to model the latent dynamics of agents’ trajectories. It then designates states with anomalous dynamics as the elusive interactive states and subsequently instructs agents to explore these states more extensively. This facilitates the emergence of interactive behaviors and promotes the learning of multi-agent policies. Experimental evaluation of SIA across various multi-agent tasks demonstrates its superior performance against multiple baselines, highlighting its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking Label-specific Features for Label Distribution Learning

arXiv

引用

arXiv 2025年

作者： Xu, Suping Dai, Chuyi Shang, Lin Shao, Changbin Yang, Xibei Pedrycz, Witold Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Department of Computer Science and Technology Nanjing University Nanjing210023 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Jiangsu University of Science and Technology Zhenjiang212003 China

Label distribution learning (LDL) is an emerging learning paradigm designed to capture the relative importance of labels for each instance. Label-specific features (LSFs), constructed by LIFT, have proven effective for learning tasks with label ambiguity by leveraging clustering-based prototypes for each label to re-characterize instances. However, directly introducing LIFT into LDL tasks can be suboptimal, as the prototypes it collects primarily reflect intra-cluster relationships while neglecting interactions among distinct clusters. Additionally, constructing LSFs using multi-perspective information, rather than relying solely on Euclidean distance, provides a more robust and comprehensive representation of instances, mitigating noise and bias that may arise from a single distance perspective. To address these limitations, we introduce Structural Anchor Points (SAPs) to capture inter-cluster interactions. This leads to a novel LSFs construction strategy, LIFT-SAP, which enhances LIFT by integrating both distance and direction information of each instance relative to SAPs. Furthermore, we propose a novel LDL algorithm, Label Distribution Learning via Label-specifIc FeaTure with SAPs (LDL-LIFT-SAP), which unifies multiple label description degrees predicted from different LSF spaces into a cohesive label distribution. Extensive experiments on 15 real-world datasets demonstrate the effectiveness of LIFT-SAP over LIFT, as well as the superiority of LDL-LIFT-SAP compared to seven other well-established algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

SLRL: Semi-Supervised Local Community Detection Based on Reinforcement Learning 39

SLRL: Semi-Supervised Local Community Detection Based on Rei...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ni, Li Ye, Rui Luo, Wenjian Zhang, Yiwen Zhang, Lei Sheng, Victor S. School of Computer Science and Technology Anhui University China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies China School of Computer Science and Technology Harbin Institute of Technology China School of Department of Computer Science Texas Tech University United States

ISBN: (纸本)157735897X

Most existing semi-supervised community detection algorithms leverage known communities to learn community structures, subsequently identifying communities that align with these learned community structures. However, differences in community structures may render the community structures learned by these methods inappropriate for the community containing the given node of interest. As a result, the identified community may exclude the given node or be of poor quality. Inspired by the success of reinforcement learning, we propose a Semi-supervised Local community detection method based on Reinforcement Learning, named SLRL, which only explores parts of the network surrounding the given node. It first extracts the local structure around a given node with an extractor, followed by selecting communities that are similar to this local structure to distill useful communities. These selected communities are employed to train the expander, which expands the community containing a given node. Experimental results demonstrate that SLRL outperforms state-of-the-art algorithms on five real-world datasets. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting

arXiv

引用

arXiv 2024年

作者： Li, Feifei Guo, Suhan Han, Feng Zhao, Jian Shen, Furao National Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Accurate forecasting of long-term time series has important applications for decision making and planning. However, it remains challenging to capture the long-term dependencies in time series data. To better extract long-term dependencies, We propose Multi-Scale Dilated Convolution Network (MSDCN), a method that utilizes a shallow dilated convolution architecture to capture the period and trend characteristics of long time series. We design different convolution blocks with exponentially growing dilations and varying kernel sizes to sample time series data at different scales. Furthermore, we utilize traditional autoregressive model to capture the linear relationships within the data. To validate the effectiveness of the proposed approach, we conduct experiments on eight challenging long-term time series forecasting benchmark datasets. The experimental results show that our approach outperforms the prior state-of-the-art approaches and shows significant inference speed improvements compared to several strong baseline methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Explaining Model Overfitting in CNNS Via GMM Clustering

SSRN

引用

SSRN 2024年

作者： Dou, Hui Mu, Xinyu Yi, Mengjun Han, Feng Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology China Department of Computer Science and Technology Nanjing University Nanjing210023 China School of Electronic Science and Engineering Nanjing University Nanjing210023 China School of Artificial Intelligence Nanjing University Nanjing210023 China

Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challenges for practical applications. In this study, we provide quantitative metrics for assessing CNN filters by clustering the feature maps corresponding to individual filters in the model via Gaussian Mixture Model (GMM). By analyzing the clustering results, we screen out some anomaly filters associated with outlier samples. We further analyze the relationship between the anomaly filters and model overfitting, proposing three hypotheses. This method is universally applicable across diverse CNN architectures without modifications, as evidenced by its successful application to models like AlexNet and LeNet-5. We present three meticulously designed experiments demonstrating our hypotheses from the perspectives of model behavior, dataset characteristics, and filter impacts. Through this work, we offer a novel perspective for evaluating the CNN performance and gain new insights into the operational behavior of model overfitting. © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SoVAR: Building Generalizable Scenarios from Accident Reports for Autonomous Driving Testing

arXiv

引用

arXiv 2024年

作者： Guo, An Zhou, Yuan Tian, Haoxiang Fang, Chunrong Sun, Yunjian Sun, Weisong Gao, Xinyu Luu, Anh Tuan Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China College of Computing and Data Science Nanyang Technological University Singapore

Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenarios from real-world accident reports provide valuable resources for ADS testing, including critical scenarios and high-quality seeds. However, existing scenario reconstruction methods from accident reports often exhibit limited accuracy in information extraction. Moreover, due to the diversity and complexity of road environments, matching current accident information with the simulation map data for reconstruction poses significant challenges. In this paper, we design and implement SoVAR, a tool for automatically generating road-generalizable scenarios from accident reports. SoVAR utilizes well-designed prompts with linguistic patterns to guide the large language model (LLM) in extracting accident information from textual data. Subsequently, it formulates and solves accident-related constraints in conjunction with the extracted accident information to generate accident trajectories. Finally, SoVAR reconstructs accident scenarios on various map structures and converts them into test scenarios to evaluate its capability to detect defects in industrial ADSs. We experiment with SoVAR, using the accident reports from the National Highway Traffic Safety Administration's (NHTSA) database to generate test scenarios for the industrial-grade ADS Apollo. The experimental findings demonstrate that SoVAR can effectively generate generalized accident scenarios across different road structures. Furthermore, the results confirm that SoVAR identified 5 distinct safety violation types that contributed to the crash of Baidu Apollo. Copyright © 2024, The Authors. All rights reserved.

关键词： Automatic test pattern generation

来源：评论

学校读者我要写书评

暂无评论

Lcvd: Loop-Oriented Code Vulnerability Detection Via Graph Neural Network

SSRN

引用

SSRN 2023年

作者： Wang, Mingke Tao, Chuanqi Guo, Hongjing College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Due to the unique mechanism and complex structure, loops in programs can easily lead to various vulnerabilities such as dead loops, memory leaks, resource depletion, etc. Traditional approaches to loop-oriented program analysis (e.g. loop summarization) are costly with a high rate of false positives in complex software systems. To address the issues above, recent works have applied deep learning (DL) techniques to vulnerability detection. However, existing DL-based approaches mainly focused on the general characteristics of most vulnerabilities without considering the semantic information of specific vulnerabilities. As a typical structure in programs, loops are highly iterative with multi-paths. Currently, there is a lack of available approaches to represent loops, as well as useful methods to extract the implicit vulnerability patterns. Therefore, this paper introduces LCVD, an automated loop-oriented code vulnerability detection approach. LCVD represents the source code as the Loop-flow Abstract Syntax Tree (LFAST), which focuses on interleaving multi-paths around loop structures. Then a novel Loop-flow Graph Neural Network (LFGNN) is proposed to learn both the local and overall structure of loop-oriented vulnerabilities. The experimental results demonstrate that LCVD outperforms the three static analysis-based and four state-of-the-art DL-based vulnerability detection approaches across evaluation settings. © 2023, The Authors. All rights reserved.

关键词： Flow graphs

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：